Offline Discovery of Interpretable Skills from Multi-Task Trajectories

• URL: http://arxiv.org/abs/2602.01018v1
• Date: Sun, 01 Feb 2026 05:03:58 GMT
• Title: Offline Discovery of Interpretable Skills from Multi-Task Trajectories
• Authors: Chongyu Zhu, Mithun Vanniasinghe, Jiayu Chen, Chi-Guhn Lee,
• Abstract summary: We introduce LOKI, a three-stage end-to-end learning framework for offline skill discovery and hierarchical imitation.<n>LOKI achieves high success rates on the challenging D4RL Kitchen benchmark and outperforms standard HIL baselines.
• Score: 8.119611773942562
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hierarchical Imitation Learning is a powerful paradigm for acquiring complex robot behaviors from demonstrations. A central challenge, however, lies in discovering reusable skills from long-horizon, multi-task offline data, especially when the data lacks explicit rewards or subtask annotations. In this work, we introduce LOKI, a three-stage end-to-end learning framework designed for offline skill discovery and hierarchical imitation. The framework commences with a two-stage, weakly supervised skill discovery process: Stage one performs coarse, task-aware macro-segmentation by employing an alignment-enforced Vector Quantized VAE guided by weak task labels. Stage two then refines these segments at a micro-level using a self-supervised sequential model, followed by an iterative clustering process to consolidate skill boundaries. The third stage then leverages these precise boundaries to construct a hierarchical policy within an option-based framework-complete with a learned termination condition beta for explicit skill switching. LOKI achieves high success rates on the challenging D4RL Kitchen benchmark and outperforms standard HIL baselines. Furthermore, we demonstrate that the discovered skills are semantically meaningful, aligning with human intuition, and exhibit compositionality by successfully sequencing them to solve a novel, unseen task.

Related papers

• Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning [19.2269680366874]
  Previous continual learning setups for embodied intelligence focused on executing low-level actions based on human commands.<n>We propose the Hierarchical Embodied Continual Learning setups (HEC) that divide the agent's continual learning process into two layers: high-level instructions and low-level actions.<n>We introduce the Task-aware Mixture of Incremental LoRA Experts (Task-aware MoILE) method.
  arXiv  Detail & Related papers  (2025-06-05T03:20:47Z)
• Spatial Reasoning and Planning for Deep Embodied Agents [2.7195102129095003]
  This thesis explores the development of data-driven techniques for spatial reasoning and planning tasks. It focuses on enhancing learning efficiency, interpretability, and transferability across novel scenarios.
  arXiv  Detail & Related papers  (2024-09-28T23:05:56Z)
• Variational Offline Multi-agent Skill Discovery [47.924414207796005]
  We propose two novel auto-encoder schemes to simultaneously capture subgroup- and temporal-level abstractions and form multi-agent skills.<n>Our method can be applied to offline multi-task data, and the discovered subgroup skills can be transferred across relevant tasks without retraining.<n> Empirical evaluations on StarCraft tasks indicate that our approach significantly outperforms existing hierarchical multi-agent reinforcement learning (MARL) methods.
  arXiv  Detail & Related papers  (2024-05-26T00:24:46Z)
• SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution [75.2573501625811]
  Diffusion models have demonstrated strong potential for robotic trajectory planning. generating coherent trajectories from high-level instructions remains challenging. We propose SkillDiffuser, an end-to-end hierarchical planning framework.
  arXiv  Detail & Related papers  (2023-12-18T18:16:52Z)
• Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning [18.496765732728164]
  We propose a novel framework, CLIS, which leverage image-level supervision to enhance the detection ability in a multi-task collaborative way. CLIS achieves an overall AP of 31.1 with 10.1 point improvement on tail categories, establishing a new state-of-the-art.
  arXiv  Detail & Related papers  (2022-10-11T16:02:14Z)
• Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization [101.72755769194677]
  We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph. Our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks. Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks.
  arXiv  Detail & Related papers  (2022-05-25T10:44:25Z)
• Hierarchical Skills for Efficient Exploration [70.62309286348057]
  In reinforcement learning, pre-trained low-level skills have the potential to greatly facilitate exploration. Prior knowledge of the downstream task is required to strike the right balance between generality (fine-grained control) and specificity (faster learning) in skill design. We propose a hierarchical skill learning framework that acquires skills of varying complexity in an unsupervised manner.
  arXiv  Detail & Related papers  (2021-10-20T22:29:32Z)
• Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification [62.10696018098057]
  We propose an easy-to-hard expert meta-training strategy to arrange the training tasks properly. A task hardness aware module is designed and integrated into the training procedure to estimate the hardness of a task. Experimental results on the miniImageNet and tieredImageNetSketch datasets show that the meta-learners can obtain better results with our expert training strategy.
  arXiv  Detail & Related papers  (2020-07-13T08:49:00Z)
• Adversarial Continual Learning [99.56738010842301]
  We propose a hybrid continual learning framework that learns a disjoint representation for task-invariant and task-specific features. Our model combines architecture growth to prevent forgetting of task-specific skills and an experience replay approach to preserve shared skills.
  arXiv  Detail & Related papers  (2020-03-21T02:08:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.